Technologies

27 pages, 1655 KB

Open AccessArticle

Multi-Model Ensemble Evaluation of Student Design Projects in Higher Education: A Comparative Analysis of AI and Human Expert Grading

by Filip Cvitić, Tajana Koren Ivančević and Nikolina Stanić Loknar

Technologies 2026, 14(7), 382; https://doi.org/10.3390/technologies14070382 (registering DOI) - 23 Jun 2026

Abstract

This study investigates the potential, limitations, and pedagogical implications of applying a parallel multi-model AI evaluation workflow, using ChatGPT, DeepSeek, and Uizard, to assess student design projects in higher education. Because design assessment involves both formal criteria and subjective creative interpretation, the study [...] Read more.

This study investigates the potential, limitations, and pedagogical implications of applying a parallel multi-model AI evaluation workflow, using ChatGPT, DeepSeek, and Uizard, to assess student design projects in higher education. Because design assessment involves both formal criteria and subjective creative interpretation, the study first established a human expert baseline based on three independent university professors. The human inter-rater reliability was low to moderate, with a mean pairwise Spearman’s ρ of 0.36 and Cronbach’s α of 0.60 for packaging design, and ρ of 0.43 and α of 0.69 for web design. This finding is central to the study, as it shows that the human benchmark in creative design assessment is itself variable and interpretive. Against this baseline, AI–human alignment remained limited and task-dependent. For packaging design, the AI ensemble showed only a weak positive association with the human expert baseline (Spearman’s ρ = 0.30, p = 0.031), which should be interpreted cautiously given the Bonferroni-adjusted significance threshold used in the study. For web design, no significant AI–human association was observed. Qualitative analysis of AI-generated rationales identified recurring limitations, including hallucination, aesthetic shield effects, and missed context, where visually polished work was rewarded despite deeper conceptual or structural weaknesses. The findings suggest that current AI systems can provide useful formative feedback on visible formal features, but they are not reliable as autonomous grading tools for complex creative work. AI-assisted assessment is therefore best understood as a supervised formative support mechanism, while final evaluation should remain grounded in human pedagogical judgment. Full article

► Show Figures

Figure 1

23 pages, 1853 KB

Open AccessArticle

Fixed-Time Control of the Lifting Axis of a CNC Machine Using a Permanent Magnet Synchronous Motor and a Fixed-Time Nonlinear Observer

by Varin Cholahan, Worapong Tangsrirat and Tattaya Pukkalanun

Technologies 2026, 14(7), 381; https://doi.org/10.3390/technologies14070381 (registering DOI) - 23 Jun 2026

Abstract

This paper introduces an adaptive fixed-time position controller (AFxTPC) designed for the lifting axis servo mechanism of a computer numerical control (CNC) plasma machine. It integrates a permanent magnet synchronous motor, gearbox, and ball screw into a unified electromechanical model. The proposed AFxTPC [...] Read more.

This paper introduces an adaptive fixed-time position controller (AFxTPC) designed for the lifting axis servo mechanism of a computer numerical control (CNC) plasma machine. It integrates a permanent magnet synchronous motor, gearbox, and ball screw into a unified electromechanical model. The proposed AFxTPC combines a fixed-time terminal sliding surface function with adaptive fixed-time sliding mode control to achieve fixed-time convergence, precise tracking, and robustness in the presence of parameter uncertainties. A specially designed reaching law guarantees accurate trajectory tracking, while the fixed-time terminal sliding surface function effectively minimizes chattering near the sliding manifold. Importantly, a novel fixed-time nonlinear disturbance observer is developed to simultaneously estimate the unmeasured system states and lumped disturbances in real time within a guaranteed initial-state-independent settling time. These estimated values are explicitly fed back into controller for active disturbance compensation. The stability of the overall closed-loop system is rigorously established using Lyapunov stability theory. Simulation results demonstrate that the proposed observer-based controller achieves superior performance compared with conventional proportional–integral–derivative (PID) and standard sliding mode controllers. It exhibits zero steady-state error, reduced overshoot, minimal chattering, and strong robustness over a wide range of operating conditions. Full article

(This article belongs to the Section Manufacturing Technology)

► Show Figures

Figure 1

27 pages, 2157 KB

Open AccessArticle

PI-Based Adaptive Actor–Critic Displacement Volume Control of Axial-Piston Pump

by Alexander Mitov, Tsonyo Slavov and Jordan Kralev

Technologies 2026, 14(6), 380; https://doi.org/10.3390/technologies14060380 (registering DOI) - 22 Jun 2026

Abstract

This article presents the synthesis, implementation, and experimental study of a PI-based adaptive actor–critic displacement volume controller of an axial-piston pump intended for open-loop circuit hydraulic drive systems. The proposed control structure combines a conventional PI actor with an adaptive critic that estimates [...] Read more.

This article presents the synthesis, implementation, and experimental study of a PI-based adaptive actor–critic displacement volume controller of an axial-piston pump intended for open-loop circuit hydraulic drive systems. The proposed control structure combines a conventional PI actor with an adaptive critic that estimates the infinite-horizon cost through Bellman-error minimization. By using the tracking error and its integral as actor inputs, the controller avoids the need for an accurate plant model while retaining a compact and practically implementable structure. The adaptive laws are derived using gradient-based learning, and a Lyapunov-based analysis establishes closed-loop stability for sufficiently small adaptation gains. The controller is implemented in a fixed-step Simulink^® environment and deployed on a rapid prototyping platform with real-time communication to an industrial microcontroller and proportional valve amplifier. The experimental results obtained under four fixed loading conditions and dynamic load variations demonstrate a stable operation, bounded critic behavior, and a near-zero Bellman error during learning. Comparative tests against a classical PI controller, a Lyapunov-based model reference adaptive controller, and a generic actor–critic scheme show that the proposed PI-based actor–critic achieves the lowest performance index and the shortest settling times in most cases. Full article

(This article belongs to the Special Issue Advances in Automatics, Robotics & Artificial Intelligence)

43 pages, 5138 KB

Open AccessArticle

Air-to-Air Flight: ANFIS-Assisted Multi-Pack LiPo Battery Charging System for Continuous Flying Missions of UAVs

by Essam Ali, Mohamed Abdelrahem, José Rodríguez, Abdelfatah M. Mohamed and Alaaeldin M. Abdelshafy

Technologies 2026, 14(6), 379; https://doi.org/10.3390/technologies14060379 (registering DOI) - 22 Jun 2026

Abstract

Continouous unmanned aerial vehicle (UAV) missions are fundamentally limited by Lithium-Polymer (LiPo) battery endurance under intermittent and power-constrained renewable energy conditions. This paper proposes an integrated energy management and charging framework for a photovoltaic (PV)-powered mobile station equipped with a hybrid energy storage [...] Read more.

Continouous unmanned aerial vehicle (UAV) missions are fundamentally limited by Lithium-Polymer (LiPo) battery endurance under intermittent and power-constrained renewable energy conditions. This paper proposes an integrated energy management and charging framework for a photovoltaic (PV)-powered mobile station equipped with a hybrid energy storage system (HESS) and an automated battery replacement (ABR) mechanism. A lexicographic priority-based allocator sequentially serves ABR actuation, multi-slot LiPo charging, and Brushless DC (BLDC) propulsion, while the HESS compensates for PV intermittency. At the charging level, a constraint-aware constant current–constant voltage (CC–CV) strategy is enhanced by an adaptive neuro-fuzzy inference system (ANFIS) trained on optimization-derived labels using battery temperature and its rate of change, thus enabling anticipatory thermal current derating with smooth, discontinuity-free control action. Anti-windup proportional–integral (PI) regulation and bumpless mode transfer ensure stable CC-to-CV transitions. An event-triggered emergency mode accelerates battery readiness via a max-first selection policy. Comparative simulations against a PSO/DE-optimized PID benchmark over a full diurnal PV cycle demonstrate that the ANFIS controller reduces the CC-mode current tracking root-mean-square error (RMSE) by up to 96.9%, delivers higher charge throughput, and lowers battery degradation proxies, including SOC-weighted thermal dose and equivalent full cycles (EFC). The proposed framework reliably sustains continuous charge–swap–recharge logistics under fluctuating renewable generation. Full article

(This article belongs to the Special Issue Artificial Intelligence for Energy Integration and Efficiency in Photovoltaic and Thermal Solar Systems)

► Show Figures

Figure 1

27 pages, 6430 KB

Open AccessArticle

A Voltage Regulation Strategy Based on Coordinated Control of Multiple Heterogeneous Devices Using Multi-Strategy Integrated Rime Optimization Algorithm

by Xiaoming Wang, Wenguang Zhao, Meichen Dong, Hao Zheng, Zidong Meng and Yingyu Liang

Technologies 2026, 14(6), 378; https://doi.org/10.3390/technologies14060378 (registering DOI) - 20 Jun 2026

Abstract

The large-scale integration of distributed photovoltaics (DPVs) into the distribution network exacerbates voltage fluctuations and substantially increases network losses. To improve the voltage quality and economic efficiency of distribution networks, a Volt/Var optimization (VVO) model is established. Coordinating multiple heterogeneous devices, the model [...] Read more.

The large-scale integration of distributed photovoltaics (DPVs) into the distribution network exacerbates voltage fluctuations and substantially increases network losses. To improve the voltage quality and economic efficiency of distribution networks, a Volt/Var optimization (VVO) model is established. Coordinating multiple heterogeneous devices, the model aims to minimize the total voltage deviation, the total network losses, and the regulation cost of discrete equipment simultaneously. Considering multi-constraint coupling characteristics, a quantitative method is proposed to evaluate the reactive power regulation potential of DPVs under intricate operating conditions. Then, the multi-strategy integrated rime optimization algorithm (MSIRIME) is utilized for the model solution. Fuch chaotic mapping generates uniformly distributed and ergodic initial populations. A dual-branch search mechanism combining the snow ablation optimizer with the rime optimization significantly enhances global exploration capabilities. The guided learning strategy balances exploration and exploitation for high-dimensional VVO, preventing local optima. Case tests on a modified IEEE 33-bus system demonstrate that the proposed model exhibits excellent effectiveness and robustness. Moreover, MSIRIME exhibits better optimization performance than some classic and recently proposed strategies, reducing the average network losses and voltage deviation over 30 independent runs by at least 5.87% and 52.22%, respectively, relative to those of the compared methods. Full article

(This article belongs to the Special Issue Next-Generation Distribution System Planning, Operation, and Control—Second Edition)

► Show Figures

Figure 1

20 pages, 297 KB

Open AccessArticle

A Hybrid Multi-Criteria Decision Framework for Internet Technology Selection in Smart Tourism Systems

by Branislav Šoškić, Dejan Viduka, Vladimir Kraguljac, Dragan Rastovac and Petra Balaban

Technologies 2026, 14(6), 377; https://doi.org/10.3390/technologies14060377 (registering DOI) - 19 Jun 2026

Abstract

The digital transformation of tourist facilities requires careful selection of technologies that can provide secure, stable and scalable network infrastructure. Due to the possibility of application in different sectors with different specificities, the focus of the research was placed on the implementation of [...] Read more.

The digital transformation of tourist facilities requires careful selection of technologies that can provide secure, stable and scalable network infrastructure. Due to the possibility of application in different sectors with different specificities, the focus of the research was placed on the implementation of smart tourist services. A hybrid multi-criteria decision-making model based on PIPRECIA and MVA models was applied for the research. Based on the literature and the opinions of experts in the field, evaluation criteria such as bandwidth, latency, energy efficiency, security and privacy, scalability, costs and interoperability were defined, and internet technologies such as Li-Fi, Wi-Fi 7, Wi-Fi 6, private 5G networks, Ethernet-over-Power (EoP), NB-IoT and LoRaWAN were defined. The results obtained put the security and privacy criterion at the top (0.2253), followed by scalability (0.1952) and bandwidth (0.1624). The obtained results indicate that Wi-Fi 7 achieved the highest weighted score (4.2247), followed closely by Li-Fi (4.2177) and Wi-Fi 6 (4.0771). Wi-Fi 7 demonstrated particularly strong performance in scalability, interoperability and bandwidth, making it highly suitable for environments with high user density. Li-Fi achieved very high scores in security and latency, which makes it particularly appropriate for security-sensitive smart tourism environments. Lower-ranked technologies such as NB-IoT and LoRaWAN proved valuable for supporting IoT and monitoring functions, rather than as primary communication infrastructure. The proposed model has proven to be a flexible, transparent and practical tool for strategic decision-making in the field of smart tourism. In addition to the basic application presented in the paper, the model has the potential to be adapted to different contexts and expanded with additional criteria or new technologies. The proposed hybrid approach can serve as a useful decision-making tool for tourism managers, system engineers and urban planners who are looking for optimal solutions for the development of digital infrastructure. Full article

(This article belongs to the Special Issue Smart Technologies Shaping the Future of Tourism and Hospitality)

43 pages, 26548 KB

Open AccessReview

Advances in Multi-Level Compensation Strategy and Process Collaborative Optimization for Robotic Belt Grinding

by Zhuoshi Li, Guili Gao, Jialin Guo and Dequan Shi

Technologies 2026, 14(6), 376; https://doi.org/10.3390/technologies14060376 (registering DOI) - 19 Jun 2026

Abstract

Robotic belt grinding is an effective and widely adopted finishing method for superalloys, offering notable advantages such as high material removal capability, low heat input, and reduced workpiece damage. In addition, robots can readily integrate multiple sensors—such as infrared radiation cameras, force sensors, [...] Read more.

Robotic belt grinding is an effective and widely adopted finishing method for superalloys, offering notable advantages such as high material removal capability, low heat input, and reduced workpiece damage. In addition, robots can readily integrate multiple sensors—such as infrared radiation cameras, force sensors, and high-speed cameras—which facilitate real-time monitoring of the grinding process and thereby enhance grinding quality control. With the establishment and continuous advancement of large-scale artificial intelligence (AI) data models, new breakthroughs have emerged in the optimization of robotic grinding processes. Owing to its dexterous workspace and advantages in high flexibility and cost-effectiveness, robotic belt grinding has become a critical process for the precision forming of complex curved components such as aero-engine blades and blisks. However, factors such as the limited absolute accuracy of industrial robots, time-varying grinding contact states, and significant transient boundary effects make it difficult for the current constant-parameter open-loop machining mode to simultaneously meet the demands for high material removal efficiency and high surface integrity on complex profiles. This paper systematically reviews the technologies for precision control and process optimization of robotic belt grinding aimed at pointwise precise material removal. First, the structural composition of the robotic belt grinding system and the material removal mechanism are analyzed. Then, centered on the compensation concept, a hierarchical progressive technical framework is outlined, covering geometric calibration compensation, force/position hybrid online compensation, transient entry boundary compensation, and system-level comprehensive compensation of multi-source errors, with a comparison of the applicable scenarios and the effects on shape and property control at each level. Furthermore, under the support of effective compensation, the collaborative optimization methods of material removal modeling, multi-objective optimization of process parameters, force-constrained trajectory planning, and intelligent adaptive processes are elaborated. Finally, current technical bottlenecks are summarized, and future trends in next-generation adaptive grinding technology driven by digital twins and embodied intelligence are envisioned. This review aims to provide a systematic theoretical reference for the high-precision and intelligent upgrading of robotic precision grinding systems. Full article

(This article belongs to the Section Manufacturing Technology)

► Show Figures

Figure 1

25 pages, 457 KB

Open AccessArticle

CAN-TEMPO: Unsupervised CAN Bus Intrusion Detection via Temporal Multi-Period Oscillation Encoding

by Soufiane Oualil, Issam Ait Yahia, Mohamed El Kamili, Khalid Fardousse and Ismail Berrada

Technologies 2026, 14(6), 375; https://doi.org/10.3390/technologies14060375 (registering DOI) - 18 Jun 2026

Abstract

The security of Controller Area Network (CAN) systems is critical for modern automotive safety, as their lack of built-in security mechanisms makes them vulnerable to cyberattacks. In this work, we propose CAN-TEMPO, an unsupervised anomaly detection framework that explicitly models the multi-periodic structure [...] Read more.

The security of Controller Area Network (CAN) systems is critical for modern automotive safety, as their lack of built-in security mechanisms makes them vulnerable to cyberattacks. In this work, we propose CAN-TEMPO, an unsupervised anomaly detection framework that explicitly models the multi-periodic structure of CAN traffic. The proposed approach leverages a Temporal Multi-Periodic Oscillation (TEMPO) block, which uses frequency-domain analysis to transform one-dimensional CAN sequences into multi-scale two-dimensional representations. This design enables the model to capture both intra-period correlations and inter-period temporal variations. We evaluate CAN-TEMPO on multiple public CAN intrusion detection benchmarks under diverse attack scenarios and generalization settings. Experimental results show that CAN-TEMPO consistently outperforms state-of-the-art methods in terms of AUC-ROC and F1-score, while maintaining lower false positive rates and improved robustness across different vehicles and attack types. These findings demonstrate that explicitly modeling periodic structures enables more reliable and generalizable anomaly detection in automotive networks. Full article

► Show Figures

Figure 1

33 pages, 5543 KB

Open AccessArticle

Structural Optimization of a Hybrid Fuzzy–Incremental Conductance MPPT Controller for Photovoltaic Systems with Battery Storage

by Ezequiel Rincon-Canalizo, David Gutiérrez-Rosales, Daniel Aguilar-Torres, Omar Jiménez-Ramírez and Rubén Vázquez-Medina

Technologies 2026, 14(6), 374; https://doi.org/10.3390/technologies14060374 (registering DOI) - 18 Jun 2026

Abstract

This study presents a hybrid controller that integrates fuzzy logic control and the Incremental Conductance method. This controller optimizes maximum power point tracking in a 330 W photovoltaic system by designing a DC-DC converter. The study evaluates how the number and distribution of [...] Read more.

This study presents a hybrid controller that integrates fuzzy logic control and the Incremental Conductance method. This controller optimizes maximum power point tracking in a 330 W photovoltaic system by designing a DC-DC converter. The study evaluates how the number and distribution of membership functions, specifically three-, five-, and seven-function configurations, affect system performance using the Integral Square Error (ISE) and Integral Absolute Error (IAE) indices. The empirical results demonstrate that the seven-function architecture yields optimal performance, minimizing ISE and IAE to 0.1155 and

7.365 \times 10^{- 4}

, respectively. Furthermore, this optimal configuration attains an energy efficiency of 99.7%, notably outperforming the baseline three-function configuration, which exhibited a worst-case efficiency of 98.9 %. To assess robustness against dynamic environmental variations, this study subjects the optimal configuration to fluctuating irradiance and temperature profiles. Additionally, an analysis of computational resource consumption reveals that the proposed hybrid controller incurs a lower computational load for rule evaluation than three controllers reported in the recent literature. These findings demonstrate the system’s structural efficiency and superior optimization capability, achieving maximized photovoltaic energy harvesting at a low computational cost. Full article

(This article belongs to the Special Issue Artificial Intelligence for Energy Integration and Efficiency in Photovoltaic and Thermal Solar Systems)

► Show Figures

Figure 1

26 pages, 3996 KB

Open AccessArticle

A Vision-Based Software Safety Monitoring Tool for Operators in RoboDK Robotic Cells: A Simulation-Based Proof-of-Concept Study Using Workspace Masks and Image Processing

by Cozmin Adrian Cristoiu, Marius-Valentin Drăgoi, Alexandra Cojocaru and Paulina Spânu

Technologies 2026, 14(6), 373; https://doi.org/10.3390/technologies14060373 (registering DOI) - 18 Jun 2026

Abstract

This article presents the development and proof-of-concept testing of a vision-based safety monitoring tool for operators in simulated robotic cells in RoboDK. The proposed method uses a virtual camera placed above the cell and image processing techniques to analyze the relationship between the [...] Read more.

This article presents the development and proof-of-concept testing of a vision-based safety monitoring tool for operators in simulated robotic cells in RoboDK. The proposed method uses a virtual camera placed above the cell and image processing techniques to analyze the relationship between the operator and the workspace swept by the robot. In an initial stage, the robot movement is recorded as a mask of the swept space, and areas irrelevant to the process can be excluded by user-defined polygons. In the monitoring stage, the operator is identified in the video stream by HSV segmentation, after which an adjustable clearance zone is generated around the detected contour. Based on the intersections between the operator, clearance, swept space mask and the mask of the current robot movement, the application provides four discrete states: SAFE, WARNING, DANGER and COLLISION. For the experimental validation in the virtual environment, the virtual contact moment is estimated separately, while the COLLISION state is defined as the intersection between the inflated operator contour and the current robot motion mask. Therefore, in this study, COLLISION does not indicate measured physical contact, but an image-based imminent-collision condition used for early warning. The test scenario was carried out in a virtual palletizing cell, which includes an articulated arm robot, conveyors, manipulated objects and a mobile dummy acting as an operator. The obtained results support the use of the method as an applicative simulation solution for the evaluation of the early detection of risk situations. The study is limited to the virtual environment and represents a basis for future research on the development of visual monitoring systems to increase safety in collaborative and industrial robotic cells. Full article

(This article belongs to the Section Manufacturing Technology)

► Show Figures

Figure 1

31 pages, 6154 KB

Open AccessArticle

Research on Underwater Robot Control Method Based on PSO-RBF-Optimized PID

by Zhuo Chen, Zhiwei Shen, Lixiong Lin, Erkang Chen, Jiechao Wang, Haowei Zhang, Jiaxun Chen, Qianjie Cheng and Peng Chen

Technologies 2026, 14(6), 372; https://doi.org/10.3390/technologies14060372 - 18 Jun 2026

Abstract

To address the limitations of traditional controllers for the considered six-degree-of-freedom multi-thruster underwater robot under strong nonlinearities and environmental disturbances, this paper proposes a particle swarm optimization–radial basis function–proportional–integral–derivative (PSO-RBF-PID) control algorithm. The proposed method combines the nonlinear identification capability of the RBF [...] Read more.

To address the limitations of traditional controllers for the considered six-degree-of-freedom multi-thruster underwater robot under strong nonlinearities and environmental disturbances, this paper proposes a particle swarm optimization–radial basis function–proportional–integral–derivative (PSO-RBF-PID) control algorithm. The proposed method combines the nonlinear identification capability of the RBF neural network, the global optimization capability of PSO, and the stable closed-loop structure of PID control, thereby enabling adaptive parameter tuning and disturbance compensation. Unlike existing PSO-PID- and RBF-based controllers, the proposed method combines offline global optimization and online adaptive gain tuning within a unified control framework. Although the framework is modular and can be extended to underwater robotic systems with different degrees of freedom by redefining the state vector, controller channels, and thrust allocation matrix, the present study validates the method through a six-degree-of-freedom multi-thruster underwater robot case study. Comparative simulations were conducted under the same model, disturbance conditions, sampling settings, and evaluation indices for six controllers: PID, cascade PID, fuzzy PID, FOPID, PSO-PID, and PSO-RBF-PID. For the considered 6-DOF multi-thruster underwater robot, PSO-RBF-PID achieved the best overall performance in steady-state error, settling time, overshoot, and IAE. This improvement is mainly attributed to the combination of PSO-based offline optimization and RBF-based online adaptive compensation. Full article

► Show Figures

Figure 1

29 pages, 38441 KB

Open AccessArticle

Sensor Fusion-Based Smart Glove for Deterministic Sign Language Recognition: An IoT-Enabled System

by Leandro Pazmiño-Ortiz, Alan Cuenca-Sánchez, Byron Loarte-Cajamarca and María Pérez

Technologies 2026, 14(6), 371; https://doi.org/10.3390/technologies14060371 - 18 Jun 2026

Abstract

Wearable technologies offer practical opportunities for assistive communication and educational support in introductory sign language learning. This paper presents an IoT-enabled smart glove for deterministic static sign language recognition over a bounded vocabulary of 15 isolated static gestures, comprising digits (0–9) and five [...] Read more.

Wearable technologies offer practical opportunities for assistive communication and educational support in introductory sign language learning. This paper presents an IoT-enabled smart glove for deterministic static sign language recognition over a bounded vocabulary of 15 isolated static gestures, comprising digits (0–9) and five vowel handshapes (A, E, I, O, U). The system is intended for foundational static gesture and posture practice and is not designed or validated for dynamic gestures, coarticulated signing, continuous sign language recognition, or sentence-level translation. The prototype integrates five 2.2-inch (55.9 mm) resistive flex sensors and an MPU6050 3-axis accelerometer, performs acquisition, exponential moving average filtering, user-specific calibration, normalization, and deterministic classification on a NodeMCU ESP32 board, and transmits selected processed variables to Arduino Cloud through MQTT for remote monitoring. A 10 s calibration routine maps user-specific open-hand and closed-fist responses into normalized flex-sensor ranges, allowing the same deterministic rule structure to operate across participants without model retraining. Experimental evaluation with 10 healthy adult participants aged 20–41 years (mean age: 27 years), all familiar with sign language and all providing written informed consent, produced a balanced dataset of 1500 labeled steady-state sensor vectors. The class-averaged recognition rate was 92.8%, and leave-one-subject-out validation produced a subject-wise accuracy of

92.80 \pm 2.03 %

, with individual participant accuracies ranging from 90.00% to 96.00%. The local embedded processing pipeline required less than 2 ms per cycle, the complete path including MQTT visualization produced approximately 150 ms end-to-end latency, and the device operated for up to 14 h using a 3.7 V, 1000 mAh Li-Po battery. The results indicate that calibrated deterministic sensor fusion can provide a low-cost, low-latency, edge-executed solution for bounded static sign-language gesture learning tasks while maintaining stable short-term subject-wise performance under controlled experimental conditions. Full article

(This article belongs to the Section Assistive Technologies)

► Show Figures

Graphical abstract

22 pages, 549 KB

Open AccessArticle

Learning from Crowds Using a Focal Loss Function: Dealing with Imbalanced Annotations

by Julian Gil-Gonzalez, David Augusto Cárdenas-Peña, Alvaro Orozco-Gutiérrez, Enrique D. Guijarro-Estelles and Andres M. Álvarez-Meza

Technologies 2026, 14(6), 370; https://doi.org/10.3390/technologies14060370 - 17 Jun 2026

Abstract

Obtaining high-quality labeled data for supervised learning is costly, motivating the use of crowdsourcing, which distributes the annotation process across multiple workers with varying levels of expertise. A key challenge in crowdsourced data is annotation sparsity, as each worker labels only a limited [...] Read more.

Obtaining high-quality labeled data for supervised learning is costly, motivating the use of crowdsourcing, which distributes the annotation process across multiple workers with varying levels of expertise. A key challenge in crowdsourced data is annotation sparsity, as each worker labels only a limited subset of instances. This sparsity can amplify class imbalance, reduce supervision for minority classes, and bias standard cross-entropy-based models toward the majority classes. To address this problem, we propose a correlated chained Gaussian process framework trained on a focal-loss-based variational objective (CCGPFL). This probabilistic framework jointly models latent ground-truth and instance-dependent annotator reliability while accounting for correlations among annotators. In addition, the focal-weighted objective mitigates the imbalance induced by sparse annotations by assigning greater importance to harder examples during training. Experiments on synthetic, semi-synthetic, and fully real multi-annotator datasets show that CCGPFL achieves competitive and often superior performance relative to state-of-the-art learning-from-crowds baselines in terms of Overall Accuracy (OA) and Area Under the ROC Curve (AUC). Full article

► Show Figures

Figure 1

38 pages, 2490 KB

Open AccessArticle

Benefits and Drawbacks of Blockchain Technology for Traceability in Coffee Supply Chain

by Christian Gómez and Benoit Garbinato

Technologies 2026, 14(6), 369; https://doi.org/10.3390/technologies14060369 - 17 Jun 2026

Abstract

This research examines stakeholders’ perspectives in Colombia and Switzerland on blockchain traceability systems in the coffee industry. Adopting the Unified Theory of Acceptance and Use of Technology (UTAUT) as an interpretive framework, the study analyzes these perceptions through the constructs of performance expectancy, [...] Read more.

This research examines stakeholders’ perspectives in Colombia and Switzerland on blockchain traceability systems in the coffee industry. Adopting the Unified Theory of Acceptance and Use of Technology (UTAUT) as an interpretive framework, the study analyzes these perceptions through the constructs of performance expectancy, effort expectancy, social influence, and facilitating conditions. Using a quantitative cross-sectional design with an exploratory scope, we survey 360 participants, comprising 60 coffee supply chain companies and 300 consumers. Results reveal that 78.3% of stakeholders consider traceability essential, yet only 46.7% are familiar with blockchain. Stakeholders identify three primary benefits: improved transparency (91.7%), fraud prevention (88.3%), and enhanced security (86.7%). However, significant barriers persist: high implementation costs (95%), limited expertise (91.7%), and lack of awareness (93.3%). Geographic differences emerge: Colombian stakeholders prioritize cost reduction and fraud prevention, while Swiss participants focus on data management and privacy protection. Among consumers, 62.7% express interest in provenance information, 56.7% are willing to pay for blockchain systems, and 59% are interested in tipping farmers. The study classifies benefits and drawbacks across nine dimensions, providing a comprehensive framework for understanding the multidimensional impacts of blockchain on the coffee supply chain. Full article

(This article belongs to the Topic Blockchain for Sustainable Supply Chains: Enhancing Transparency from Producer to Consumer)

► Show Figures

Figure 1

18 pages, 9033 KB

Open AccessArticle

Geometry Design for Deterministic Dissipative Kerr Soliton Generation in Dual-Coupled Microresonators

by Andrés F. Calvo-Salcedo, Marin B. Marinov, Neil Guerrero González and Jose A. Jaramillo-Villegas

Technologies 2026, 14(6), 368; https://doi.org/10.3390/technologies14060368 - 17 Jun 2026

Abstract

Deterministic generation of dissipative Kerr solitons (DKSs) is a key requirement for practical microresonator-based frequency comb sources. Here, we present a design methodology for Si₃N₄ dual-coupled microring resonators (DCMs) that relates device geometry to the intrinsic and interaction parameters governing [...] Read more.

Deterministic generation of dissipative Kerr solitons (DKSs) is a key requirement for practical microresonator-based frequency comb sources. Here, we present a design methodology for Si₃N₄ dual-coupled microring resonators (DCMs) that relates device geometry to the intrinsic and interaction parameters governing soliton formation. In particular, the auxiliary-ring geometry controls the avoided mode crossing, enabling targeted control of the interaction strength a and its modal position b through geometric design and refractive-index tuning. The resulting DCM configurations exhibit accessible DKS regions in the

(Δ, | S |^{2})

parameter space under constant pump power and linear detuning sweeps. These results provide a practical framework for the implementation of robust microresonator frequency comb sources with simplified control. Full article

(This article belongs to the Special Issue Advanced Resonators and Metamaterials for High-Sensitivity Sensing and Frequency-Selective Systems)

► Show Figures

Figure 1

40 pages, 1379 KB

Open AccessSystematic Review

Post-Quantum Transition in Blockchain Architectures: A Systematic Review of Cross-Layer Security, Performance, and Governance Constraints

by Evgeniya Ishchukova, Faezeh Sadat Sajadi, Sergei Petrenko, Alexey Petrenko and Alexey Nekrasov

Technologies 2026, 14(6), 367; https://doi.org/10.3390/technologies14060367 - 17 Jun 2026

Abstract

We performed a cross-layer, system-level analysis of the post-quantum transition of blockchain architectures through a systematic review. The analysis, based on 108 peer-reviewed studies, moves beyond post-quantum cryptography (PQC) as merely a primitive substitution and examines how quantum pressures cascade through validation, propagation, [...] Read more.

We performed a cross-layer, system-level analysis of the post-quantum transition of blockchain architectures through a systematic review. The analysis, based on 108 peer-reviewed studies, moves beyond post-quantum cryptography (PQC) as merely a primitive substitution and examines how quantum pressures cascade through validation, propagation, interoperability, governance, and regulatory layers. Empirical results show that the authenticated payloads for lattice signatures grow from ~65–73 bytes (ECDSA) up to kilobyte-scale sizes, and verification overhead is increased by a factor of 2× to 5× depending on the deployment scenario. Such inflation can narrow block-capacity margins, increase propagation delay under fixed-interval regimes, and shift validator resource thresholds in heterogeneous networks. Moreover, the harvest-now–decrypt-later model creates a temporal asymmetry between the design options and the exposure window. These findings indicate that post-quantum resilience depends more on maintaining a structural balance among the tightly coupled technical and institutional stress channels than on the strength of the algorithm itself, and migration success ultimately depends on the ability to coordinate the management of these constraints, rather than on managing them separately. Full article

(This article belongs to the Special Issue Application and Management of Blockchain Technologies)

► Show Figures

Figure 1

25 pages, 12394 KB

Open AccessArticle

Process over Skill: Testing Kasparov’s Law and Coordination Protocols in Hybrid Human–AI Decision-Making for Medical Diagnosis

by Alessia Papale, Gloria Lopiano, Andrea Campagner and Federico Cabitza

Technologies 2026, 14(6), 366; https://doi.org/10.3390/technologies14060366 - 17 Jun 2026

Abstract

Artificial intelligence (AI) is increasingly being integrated into Clinical Decision-Support Systems (CDSSs), shifting attention from algorithmic performance alone to the broader sociotechnical conditions that shape effective human–AI collaboration. In this study, we investigated whether nine displacement-based structured coordination protocols can improve the collective [...] Read more.

Artificial intelligence (AI) is increasingly being integrated into Clinical Decision-Support Systems (CDSSs), shifting attention from algorithmic performance alone to the broader sociotechnical conditions that shape effective human–AI collaboration. In this study, we investigated whether nine displacement-based structured coordination protocols can improve the collective diagnostic decision-making of hybrid human–AI teams (16 board-certified radiologists and a simulated AI model) in a radiological double-reading task for vertebral fracture detection from X-ray images. Among the protocols tested, the Accuracy-Oriented, Confidence-Oriented, and Presumptuous strategies achieved the highest (balanced) accuracy overall, with up to 97% among strong clinicians and 92% among weak ones, significantly outperforming simpler methods like majority voting. Conversely, approaches optimized for a single metric (e.g., sensitivity or specificity) introduced performance trade-offs. Benefits were strongest among less proficient clinicians, which exhibited substantial and consistent improvements, while proficient clinicians showed limited gains and occasional declines. Critically, Kasparov’s Law emerged as a comparative framework for empirically evaluating coordination quality relative to the diagnostic task, clinical objective, and clinician proficiency by identifying situations in which less proficient clinicians supported by superior coordination protocols outperformed more proficient clinicians operating under inferior ones. These findings demonstrate that coordination design is a critical determinant of hybrid human–AI decision-making, highlighting that a well-structured process can be more relevant than individual components’ performance and support process-centered approaches to the development and evaluation of CDSSs. Full article

(This article belongs to the Special Issue Human–AI Collaboration: Emerging Technologies and Applications)

► Show Figures

Figure 1

24 pages, 9055 KB

Open AccessArticle

Efficient Frontier Selection via Reinforcement Learning for Exploring Unstructured Environments with Minimal Sensing

by Javier Melero-Deza, Pedro Arias-Perez, Guillermo García Patiño Lenza, Martin Molina and Pascual Campoy

Technologies 2026, 14(6), 365; https://doi.org/10.3390/technologies14060365 - 16 Jun 2026

Abstract

In recent years, reinforcement learning (RL) has been applied to frontier-based exploration to enhance a robot’s decision-making policy and improve exploration performance. In this work, we address this scenario with the aim of pushing forward the finding of the optimal frontier selection policy [...] Read more.

In recent years, reinforcement learning (RL) has been applied to frontier-based exploration to enhance a robot’s decision-making policy and improve exploration performance. In this work, we address this scenario with the aim of pushing forward the finding of the optimal frontier selection policy in unknown, unstructured environments, with RL deployed for a minimal sensing drone setup. We propose a novel policy architecture, featuring an attention module that uses the global map features captured by a convolutional neural network together with local frontier features in the form of scalar values, trained end-to-end with a scoring network using the Proximal Policy Optimization algorithm over a 2D randomized unstructured environment. Our approach demonstrates improved exploration efficiency in the evaluated scenarios, as it surpasses purely heuristic-based frontier selection strategies used as baselines for other RL methods, achieving shorter paths than the Nearest Frontier, the Hybrid Approach, and the TARE local horizon, as well as one-shot sim-to-real policy deployment. Full article

► Show Figures

Figure 1

32 pages, 9236 KB

Open AccessArticle

Edge Beats: An Edge-Computing Framework for Distributed Heart-Rate Monitoring with Low-Cost Smartwatches

by Basem Almadani, Md Moazzem Hossain, Nafisa Tabassum and Farouq Aliyu

Technologies 2026, 14(6), 364; https://doi.org/10.3390/technologies14060364 - 15 Jun 2026

Abstract

Smartwatches are increasingly used in safety-critical scenarios, yet their optical heart-rate (HR) measurements often contain noise, artifacts, and missing data, undermining clinical trust. This paper presents Edge Beats, a data-curation layer and end-to-end architecture that enables the low-cost, open source PineTime smartwatch to [...] Read more.

Smartwatches are increasingly used in safety-critical scenarios, yet their optical heart-rate (HR) measurements often contain noise, artifacts, and missing data, undermining clinical trust. This paper presents Edge Beats, a data-curation layer and end-to-end architecture that enables the low-cost, open source PineTime smartwatch to function as a practical HR sensing node for distributed wearable systems. Heart-rate packets are streamed from PineTime to an ESP32 at the edge layer over Bluetooth Low Energy (BLE), then forwarded via an embedded Message Queuing Telemetry Transport (MQTT) broker to an edge server laptop for processing and visualization. A lightweight multi-stage algorithm cleans and smooths the HR stream using physiological boundary checks, a configurable data imputation technique, and exponential moving average (EMA) smoothing, all designed for real-time operation on resource-constrained hardware. We have evaluated the system over long monitoring sessions and compared the processed PineTime output against a commercial Huawei GT Pro 2 smartwatch. The system suppresses extreme spikes and short-term oscillations, yielding a more stable HR trace with qualitative agreement to the reference trends while keeping values in a physiologically plausible range. Network measurements show low latency (almost 3 ms one-way, 15 ms RTT) and stable throughput, and power measurements (100–450 mW for ESP32 and 3–70 mW for PineTime watch) confirm that continuous HR streaming over BLE and MQTT is feasible within the PineTime’s energy budget. These results imply that data stream processing combined with a modest publish–subscribe architecture improves the stability and usability of HR streams obtained from commodity wearable sensors, making PineTime a candidate as a complementary component for mission-critical health and safety systems. Full article

(This article belongs to the Special Issue IoT-Enabling Technologies and Applications—2nd Edition)

► Show Figures

Graphical abstract

Journal Description

Technologies

Latest Articles

Journal Menu

Journal Browser

Highly Accessed Articles

Latest Books

E-Mail Alert

News

Topics

Conferences

Special Issues

Topical Collections

Further Information

Guidelines

MDPI Initiatives

Follow MDPI